Presentation: Batch Intelligence at Scale: Cost-Efficient Multi-Agent LLM Workflows with Built-In Resilience
Aditya Mulik explains how Walmart Global Tech deployed multi-agent LLM workflows across 4,700 stores for nightly batch inventory forecasting. He discusses tackling production hurdles - schema violations, cross-department data mismatches, and network drops - via MCP grounding and loop agents, while slashing cloud inference costs from $100k+ to $10k per month shifting from PTUs to pay-as-you-go. By…
Walmart Global Tech has developed a multi-agent LLM workflow to improve inventory forecasting across thousands of stores, aiming to reduce costs and increase resilience. The challenge lies in accurately predicting inventory needs for different departments in anticipation of events like Thanksgiving. While existing machine learning models can forecast demand based on historical sales data, they struggle with unexpected events such as storms.
To address this, the team created a sequential workflow of agents that integrate real-time data with existing forecasting models. This approach allows for more accurate inventory predictions at scale, while also providing built-in resilience to handle unforeseen circumstances.
Written by urgent.news from InfoQ's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
